Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     können
    -0.07
    リスト
    -0.07
     infinite
    -0.06
     neurop
    -0.06
    �蛛
    -0.06
     Oprah
    -0.06
    LLU
    -0.06
     diluted
    -0.06
     almost
    -0.06
    hesion
    -0.06
    POSITIVE LOGITS
    .Se
    0.07
    (startDate
    0.07
    _pose
    0.07
     ******************************************************************************↵
    0.07
     відповідаль
    0.07
    chai
    0.06
    ̉
    0.06
    VALID
    0.06
    _RESERVED
    0.06
    _serializer
    0.06
    Act Density 0.011%

    No Known Activations